Abstract
Multi-omics data is used in oncology to improve cure rates, decrease mortality, and prevent disease progression. However, the heterogeneity, high dimensionality, and small sample sizes of this data pose challenges for modeling tumor-gene relationships. Current research focuses on inter-omics fusion, neglecting intra-omics fusion, which results in inadequate feature representation. Dimension reduction is also important to avoid overfitting due to the high dimensionality and limited samples in omics data fusion. Thus, we proposed a novel sparse fusion representation method based on VAE-NN network and applied it into GTCN to constitute a new model named MOVNG for pan-cancer classification and biomarker identification. The presented method implements inter- and intra-omics data fusion in high-level feature space. At the same time, it can be used for a universal integration framework in which different data have the traits of heterogeneity. Extensive experiments were conducted to our combined model. From it, we can know that the sparse fusion representation method has a strong ability of expression and the model achieved an average accuracy of 92.06 ± 1.50% in 33 types of tumor classification tasks. Finally, the model also identified some vital biomarkers based on the characteristics of pan-cancer.
☆ The source code at https://github.com/cx-333/MOVNG.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
The full name of abbreviations in the figure can be found on the website (https://gdc.cancer.gov/resources-tcga-users/tcga-code-tables/tcga-study-abbreviations).
References
Berger, B., Peng, J., Singh, M.: Computational solutions for omics data. Nature Reviews Genetics
Vasaikar, S.V., Peter, S., Jing, W., Bing, Z.: LinkedOmics: analyzing multi-omics data within and across 32 cancer types. Nucleic Acids Res. D1, D1 (2017)
Huang, S., Kumardeep, C., Garmire, L.X.: More is better: recent progress in multi-omics data integration methods. Front. Genet. 8, 84 (2017)
Huang, Z., Zhan, X., Xiang, S., Johnson, T.S., Huang, K.: Salmon: Survival analysis learning with multi-omics neural networks on breast cancer. Front. Genet. 10, 166 (2019)
Chkifa, A., Cohen, A., Schwab, C.: Breaking the curse of dimensionality in sparse polynomial approximation of parametric pdes. Journal de Math ematiques Pures et Appliqu ́ees, 103(2), 400–428 (2015)
Gupta, P., Malhi, A.K.: Using deep learning to enhance head and neck cancer diagnosis and classification. In: 2018 IEEE International Conference on System, Computation, Automation and Networking (ic-scan) (2018)
Speicher, N.K., Pfeifer, N.: Towards multiple kernel principal component analysis for integrative analysis of tumor samples. J. Integr. Bioinform. 14(2), 20170019 (2017)
Xu, J., Mu, H., Yun, W., Huang, F.: Feature genes selection using supervised locally linear embedding and correlation coefficient for microarray classification. In: Computational and Mathematical Methods in Medicine, 2018, (2018–1–31), vol. 2018, pp. 1–11 (2018)
Wu, Y., Ji, R., Ge, M., Shi, S.: Classification of tumor gene expression data based on manifold learning and gaussian process. In: 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) (2019)
Liu, H., Zhang, Z., Xin, Z., Yang, Y., Zhang, C.: Dimensionality reduction for identification of hepatic tumor samples based on terahertz time-domain spectroscopy. IEEE Trans. Terahertz Sci. Technol. PP(99), 1–7 (2018)
Zhong, Y., Jia, S., Hu, Y.: Denoising auto-encoder network combined classification module for brain tumors detection. In: 2022 3rd International Conference on Electronic Communication and Artificial Intelligence (IWECAI)
Picard, M., Scott-Boyer, M.P., Bodein, A., P ́erin, O., Droit, A.: Integration strategies of multi-omics data for machine learning analysis. Comput. Struct. Biotechnol. J. 19, 3735–3746 (2021)
Acharjee, A., Kloosterman, B., Visser, R., Maliepaard, C.: Integration of multi-omics data for prediction of phenotypic traits using random forest. BMC Bioinformatics 17(5), 180 (2016)
Argelaguet, R., et al.: Multi-omics factor analysis—a framework for unsupervised integration of multi-omics data sets. Mol. Syst. Biol. 14(6), e8124 (2018)
Chaudhary, K., Poirion, O.B., Lu, L., Garmire, L.X.: Deep learning based multi-omics integration robustly predicts survival in liver cancer. Clin. Cancer Res. 24(6), 1248–1259 (2017)
Wiel, M., Lien, T.G., Verlaat, W., Wieringen, W., Wilting, S.M.: Better prediction by use of co-data: adaptive group-regularized ridge regression. Stat. Med. 35(3), 368–381 (2016)
Huda, S., Yearwood, J., Jelinek, H.F., Hassan, M.M., Fortino, G., Buckland, M.: A hybrid feature selection with ensemble classification for imbalanced healthcare data: a case study for brain tumor diagnosis. IEEE Access PP, 1 (2016)
Way, G.P., Greene, C.S.: Extracting a biologically relevant latent space from cancer transcriptomes with variational autoencoders, pp. 80–91 (2018)
Titus, A.J., Bobak, C.A., Christensen, B.C.: A new dimension of breast cancer epigenetics - applications of variational autoencoders with dna methylation. In: International Conference on Bioinformatics Models (2018)
Wang, Z., Wang, Y.: Exploring dna methylation data of lung cancer samples with variational autoencoders. In: 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (2019)
Li, Y., Kang, K., Krahn, J.M., Croutwater, N., Kevin, L.: A comprehensive genomic pan-cancer classification using the cancer genome atlas gene expression data. BMC Genomics (2017)
Zhang, X., Zhang, J., Sun, K., Yang, X., Dai, C., Guo, Y.: Integrated multi-omics analysis using variational autoencoders: Application to pan-cancer classification (2019)
Lyu, B., Haque, A.: Deep learning based tumor type classification using gene expression data (2018)
Rhee, S., Seo, S., Kim, S.: Hybrid approach of relation network and localized graph convolutional filtering for breast cancer subtype classification (2017)
Wang, T., et al.: Mogonet integrates multi-omics data using graph convolutional networks allowing patient classification and biomarker identification. Nat. Commun. 12(1), 3445 (2021)
Mahmud, M.S., Huang, J.Z., Fu, X.: Variational autoencoder-based dimensionality reduction for high-dimensional small-sample data classification. In: International Journal of Computational Intelligence and Applications, no. 1, p. 2050002 (2020)
Shi, Q., et al.: Pattern fusion analysis by adaptive alignment of multiple heterogeneous omics data. Bioinformatics 33(17), 2706–2714 (2017)
Wu, N., Wang, C.: GTNet: A tree-based deep graph learning architecture (2022)
Kingma, D., Ba, J.: Adam: A method for stochastic optimization. Computer Science (2014)
Rehman, F.U., Abbas, M., Murtaza, S., Butt, W.H., Rehman, S.: Similarity-based missing values filling algorithm. In: IEEE Thirteenth International Conference on Digital Information Management (ICDIM) (2018)
Hossin, M., Sulaiman, M.N.: A review on evaluation metrics for data classification evaluations. Int. J. Data Mining Knowl. Manag. Process 5(2), 1 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, X., Tie, Y., Liu, F., Zhang, D., Qi, L. (2023). MOVNG: Applied a Novel Sparse Fusion Representation into GTCN for Pan-Cancer Classification and Biomarker Identification. In: Huang, DS., Premaratne, P., Jin, B., Qu, B., Jo, KH., Hussain, A. (eds) Advanced Intelligent Computing Technology and Applications. ICIC 2023. Lecture Notes in Computer Science, vol 14086. Springer, Singapore. https://doi.org/10.1007/978-981-99-4755-3_52
Download citation
DOI: https://doi.org/10.1007/978-981-99-4755-3_52
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-4754-6
Online ISBN: 978-981-99-4755-3
eBook Packages: Computer ScienceComputer Science (R0)